Features
Multi-agent architecture: Archivist, Writer, Editor with separate roles
Dynamic fact extraction and Canon updates per scene
Context engine with BM25 + keyword overlap scoring
Token budget allocation for rules, cards, facts, summaries, drafts
Git-friendly storage: YAML, Markdown, JSONL
Fully offline authoring (internet only for enhancements)
Five-stage writing flow: scene preparation, context construction, draft generation, revision loop, analysis
Scene Brief generation by Archivist agent
Streaming draft generation by Writer agent
Patch-based revision preview by Editor agent
Scene fact extraction and Canon archival
Local-first, no account required for full use
Multi-device sync via account (optional)
Anime-style image generation with detailed prompts
Advanced AI settings: samplers, steps, guidance, seed
Image2Image editing for detail refinement
Enhance feature to increase resolution/detail
Inpainting to correct or add new details
Vibe Transfer to apply aesthetic from one image to another
Multiple character prompts for distinct characters
Random prompt inspiration generator
Background removal, line art, sketch, colorize, emotion tools
Writing assistant for creative storytelling
30 free initial generations
Unlimited standard images on Scroll and Opus
Up to 1024x1024 image resolution
Anlas currency system for extra features/high-res
Natural language or tag-based prompting
